Temperature control method, system and storage medium for split toilet production

Abstract

The present application relates to the technical field of temperature control, and in particular to a temperature control method and system for split toilet production and a storage medium. The method comprises the following steps: collecting temperature data and environmental variable data of each region of a kiln in real time, generating an initial temperature field mapping, and calculating the output difference index of each control unit based on the mapping; analyzing the coordination between control units, determining the coordination loss area, and adjusting the control unit sequence; calculating the connection parameters for the control unit sequence to obtain a set of smooth transition parameters, optimizing temperature regulation, and determining the uniform distribution target achievement degree through overall temperature data analysis; adjusting the collection frequency of the sensor network according to the uniform distribution target, and generating an optimized temperature field mapping. The present application solves the problem that traditional temperature control methods cannot effectively respond to kiln temperature fluctuations and uneven distribution, and realizes precise control and optimization of the temperature field, significantly improving the temperature control stability of the split toilet production process and product quality.

Description

Technical Field

[0001] This invention relates to the field of temperature control technology, and in particular to a temperature control method, system and storage medium for the production of split toilets. Background Technology

[0002] In the production of two-piece toilets, kiln temperature control is a key factor affecting product quality and production efficiency. Traditional temperature control methods typically rely on a single temperature control unit, which often struggles to cope with the challenges of large-scale temperature variations within the kiln and changes in the external environment. Due to the complex temperature field inside the kiln and the lag in heat transfer, temperature unevenness can lead to uneven sintering of ceramic materials, thereby affecting the toilet's appearance and strength.

[0003] Currently, most methods for controlling the temperature field of kilns rely on local adjustments. However, due to significant differences in temperature requirements across different areas and poor coordination between control units, it is often impossible to achieve a uniform temperature distribution throughout the kiln. This leads to localized overheating or undercooling, resulting in energy waste and extended production cycles. Furthermore, traditional temperature control systems often lack real-time feedback mechanisms, making it impossible to dynamically adjust to constantly changing environmental conditions such as humidity, airflow, and air pressure.

[0004] Therefore, achieving precise temperature field control during kiln production, especially in the production of two-piece toilets, to optimize temperature distribution, improve temperature control efficiency, and reduce energy consumption, has become a current technological challenge. This invention addresses these issues by proposing a temperature control method, system, and storage medium based on a sensor network. The aim is to optimize temperature distribution through precise temperature field control, ensuring temperature stability during the production of two-piece toilets, improving product quality, and saving energy consumption. Summary of the Invention

[0005] This invention provides a temperature control method, system, and storage medium for the production of split toilets. By precisely regulating the temperature field, it solves the problem of uneven temperature control in the kiln, avoids local overheating or undercooling, and ensures uniform sintering and high-quality production of toilet ceramics.

[0006] In a first aspect, the present invention provides a temperature control method for the production of split toilets, the method comprising: Step S1: Collect temperature data and environmental variable data of each area of ​​the kiln in real time during the production of the split toilet through a sensor network, and extract temperature field distribution characteristics from the temperature data to obtain the initial temperature field mapping. Step S2: Calculate the output difference index between the output temperature value and the expected temperature target value of each control unit according to the initial temperature field mapping. Analyze the coordination between control units based on the difference index and the neural network model, determine the coordination gap area, and obtain the coordination gap index. Step S3: If the coordination missing index exceeds a preset threshold, real-time environmental variables are obtained from the dynamic environment, and the environmental variable data is fused to determine the control unit sequence that needs to be adjusted; Step S4: Calculate the connection parameters for the control unit sequence to obtain a smooth transition parameter set; update the output settings of multiple control units through the smooth transition parameter set to determine whether the temperature fluctuation deviation has decreased; if the deviation reduction is confirmed, obtain the overall temperature data of the kiln and analyze the data distribution uniformity to determine the degree of achievement of the uniform distribution target; Step S5: Adjust the acquisition frequency of the sensor network according to the degree of achievement of the uniform distribution target to obtain the optimized temperature field mapping.

[0007] As a preferred embodiment of the present invention, step S1 includes: During the production of the split toilet, a sensor network deployed in various areas of the kiln monitors temperature changes and environmental variables in real time. Multiple temperature data points and corresponding environmental conditions are acquired from the sensor network. Feature extraction is performed on the temperature data to analyze the spatiotemporal characteristics of temperature distribution in each area. A temperature field distribution model is constructed based on these spatiotemporal characteristics to generate the initial temperature field mapping. The environmental variable data is preprocessed to filter out noise interference and retain influencing factors related to the temperature field. The preprocessed environmental variable data is then associated and stored with the initial temperature field mapping.

[0008] As a preferred embodiment of the present invention, step S2 includes: Temperature distribution data corresponding to each control unit is extracted from the initial temperature field mapping; the deviation between the output temperature value of each control unit and the expected temperature target value is compared to calculate the output difference index; the output difference index is processed using a pre-trained neural network model to analyze the coordination between control units; the coordination missing probability value of each region is output through the neural network model; the location and range of the coordination missing region are determined based on the coordination missing probability value; key features are extracted from the coordination missing region to generate the coordination missing index; the coordination missing index is compared with historical data to verify its accuracy.

[0009] As a preferred embodiment of the present invention, step S3, determining the sequence of control units that need to be adjusted by integrating the environmental variable data, includes: The system monitors the changing trend of the coordination missing index in real time; if the coordination missing index exceeds a preset threshold, an environmental variable acquisition mechanism is triggered; real-time humidity, airflow, and pressure data are acquired from the dynamic environment of the kiln through the sensor network; the real-time environmental variable data are standardized to eliminate dimensional differences; the standardized environmental variable data are fused with the initial temperature field to analyze the influence of the environment on the temperature field; based on the analysis results, control units related to the coordination missing area are determined, and the sequence of control units that need to be adjusted is generated.

[0010] As a preferred embodiment of the present invention, in step S4, the connection parameters are calculated for the control unit sequence to obtain a set of smooth transition parameters, including: Extract the current output parameters of each unit from the sequence of control units that need adjustment; analyze the output connection relationship between each control unit using a fuzzy logic algorithm; calculate the connection parameter values ​​between each control unit according to the fuzzy logic algorithm; extract smooth transition features from the connection parameter values ​​to generate the smooth transition parameter set; verify the applicability of the smooth transition parameter set under different operating conditions; balance the output differences between each control unit and optimize the temperature field distribution by using the smooth transition parameter set.

[0011] As a preferred embodiment of the present invention, step S4 involves updating the output settings of multiple control units using the smooth transition parameter set, including: The output power and response time of each control unit are adjusted according to the smooth transition parameter set; the output status of each control unit is monitored in real time after the update, and temperature fluctuation data is recorded; the fluctuation amplitude and frequency characteristics are extracted from the temperature fluctuation data; the change trends of the fluctuation amplitude and frequency characteristics before and after the update are compared; the temperature fluctuation deviation is determined according to the change trend; if the temperature fluctuation deviation is reduced, a deviation reduction confirmation signal is generated; and the deviation reduction confirmation signal is fed back to the control system.

[0012] As a preferred embodiment of the present invention, step S4, analyzing the uniformity of data distribution to determine the degree of achievement of the uniform distribution target, includes: Upon receiving the deviation reduction confirmation signal, the overall temperature data acquisition process is triggered; real-time temperature data of each area within the kiln is acquired through the sensor network; spatial distribution analysis is performed on the real-time temperature data to extract uniformity features; an information processing algorithm is used to calculate the matching degree between the uniformity features and the target uniform distribution; the degree of achievement of the uniform distribution target is determined based on the matching degree; the degree of achievement of the uniform distribution target is compared with historical records to analyze the sustainability of temperature field optimization.

[0013] As a preferred embodiment of the present invention, step S5, obtaining the optimized temperature field mapping, includes: The temperature field stability index is extracted from the uniform distribution target achievement degree; the direction of the acquisition frequency adjustment is determined based on the comparison result of the stability index and the preset threshold; if the stability index is lower than the preset threshold, the acquisition frequency of the sensor network is increased; if the stability index is higher than the preset threshold, the acquisition frequency of the sensor network is decreased; temperature data and environmental variable data are reacquired according to the adjusted acquisition frequency; the temperature field distribution characteristics are updated from the reacquired data to generate the optimized temperature field mapping; the coordinated control mechanism of the kiln temperature field is maintained through the optimized temperature field mapping.

[0014] Secondly, the present invention also provides a temperature control system for the production of split toilets, used to implement the above-mentioned method, the system comprising: The temperature mapping unit is used to collect temperature data and environmental variable data of various areas of the kiln in real time during the production of split toilets through a sensor network, and extract temperature field distribution characteristics from the temperature data to obtain an initial temperature field mapping. The difference analysis unit is used to calculate the output difference index between the output temperature value and the expected temperature target value of each control unit according to the initial temperature field mapping, analyze the coordination between control units based on the difference index and the neural network model, determine the coordination missing area and obtain the coordination missing index. The data fusion unit is used to obtain real-time environmental variables from the dynamic environment and fuse the environmental variable data to determine the sequence of control units that need to be adjusted if the coordination missing index exceeds a preset threshold. The output adjustment unit is used to calculate the connection parameters for the control unit sequence to obtain a smooth transition parameter set; update the output settings of multiple control units through the smooth transition parameter set to determine whether the temperature fluctuation deviation has decreased; if the deviation reduction is confirmed, acquire the overall temperature data of the kiln and analyze the data distribution uniformity to determine the degree of achievement of the uniform distribution target; A frequency adjustment unit is used to adjust the acquisition frequency of the sensor network according to the degree of achievement of the uniform distribution target, so as to obtain an optimized temperature field mapping.

[0015] Thirdly, the present invention provides a computer-readable storage medium storing instructions that, when executed by a processor, implement the above-described method.

[0016] The beneficial effects of this invention are as follows: This invention uses a sensor network to collect real-time temperature and environmental variable data from various areas of the kiln and generates an initial temperature field mapping, providing a foundation for subsequent temperature control adjustments. This helps to clarify temperature differences between different areas and identify potential temperature unevenness issues. Next, by analyzing the initial temperature field mapping data, the difference index between the output temperature of each control unit (such as the heating element) and the expected temperature target value is calculated. Combined with a neural network model, the coordination between control units is further analyzed to identify areas of coordination deficiency requiring adjustment, providing a basis for adjustment schemes. When a coordination deficiency area is identified, real-time environmental variables such as humidity and airflow are obtained from the dynamic environment, and the above data is integrated to optimize and adjust the temperature control strategy. This dynamically determines which control units need adjustment, forming a new control unit sequence. Furthermore, connection parameters are calculated, and the output settings of multiple control units are optimized and adjusted through a smooth transition parameter set, thereby reducing temperature fluctuation deviations. By determining whether temperature fluctuations have decreased, the stability and uniformity of the temperature field are ensured. After optimizing the output settings of the control unit, the degree of achievement of temperature field optimization is further determined by analyzing the distribution uniformity of the overall temperature data. The acquisition frequency of the sensor network is adjusted according to the degree of uniform distribution target achievement. Through adaptive adjustment of the acquisition frequency, the temperature distribution can be monitored more accurately in real time, and an optimized temperature field mapping can be generated according to needs. Through the cooperation of the above technical solutions, the temperature control system can continuously provide uniform and accurate temperature regulation during the production of two-piece toilets. This not only optimizes the temperature control accuracy, reduces energy consumption, and improves production efficiency, but also copes with the challenges of different production stages and environmental conditions, ensuring that each link operates in the optimal state, and ultimately achieving the production of high-quality two-piece toilets. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the temperature control method for the production of split toilets in this embodiment; Figure 2 and Figure 3 These are schematic diagrams of the control unit's output power and corresponding connection relationships; Figure 4 This is a schematic diagram of the temperature control system architecture for the entire process of manufacturing a split-type toilet, as shown in the example. Figure 5 This is a structural diagram of the temperature control system for the production of the split toilet in this embodiment. Detailed Implementation

[0019] This invention provides a temperature control method, system, and storage medium for the production of split-type toilets. The terms "first," "second," "third," "fourth," etc. (if applicable) in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] For ease of understanding, the specific process of the embodiments of the present invention will be described below, such as... Figure 1 As shown, the temperature control method for manufacturing split toilets in this embodiment of the invention includes: Step S1: Real-time collection of temperature data and environmental variable data from various areas of the kiln during the production of split toilets via a sensor network; extraction of temperature field distribution characteristics from the temperature data to obtain an initial temperature field mapping; specifically including: During the production of the split toilet, a sensor network deployed in various areas of the kiln monitors temperature changes and environmental variables in real time. Multiple temperature data points and corresponding environmental conditions are acquired from the sensor network. Feature extraction is performed on the temperature data to analyze the spatiotemporal characteristics of temperature distribution in each area. A temperature field distribution model is constructed based on these spatiotemporal characteristics to generate the initial temperature field mapping. The environmental variable data is preprocessed to filter out noise interference and retain influencing factors related to the temperature field. The preprocessed environmental variable data is then associated and stored with the initial temperature field mapping.

[0021] Specifically, in the production process of two-piece toilets, the temperature and environmental conditions in different areas of the kiln have a significant impact on production quality. Since the toilets are made of ceramic, a sensor network is needed to monitor temperature changes and environmental variables in different areas of the kiln in real time. To this end, the sensor network is deployed in key locations such as the preheating zone, firing zone, and cooling zone of the kiln. Each zone is equipped with multiple temperature and environmental sensors to ensure comprehensive coverage of temperature changes within the kiln and to capture environmental conditions such as humidity and airflow in real time. The multi-point data acquired by the sensor network is first used to form a time-series dataset of temperature and environmental variables. Temperature data is recorded at set intervals, while environmental variables include oxygen content, airflow, and pressure parameters. Subsequently, feature extraction is performed on the temperature data to analyze the spatiotemporal characteristics of temperature distribution in each area. Specifically, Fourier transform is performed on the temperature data to convert the time-domain signal into a frequency-domain signal, extracting the periodic patterns of temperature fluctuations. Then, Moran's I index is used to analyze the spatiotemporal correlation of temperature distribution in each area, assessing the degree of clustering or uniformity of temperature distribution in each area. The I-index is a spatial autocorrelation statistic that assesses the uniformity or clustering of the overall distribution by comparing the similarity of temperature values ​​in adjacent regions. A positive value indicates positive correlation, and a negative value indicates negative correlation. Based on the above spatiotemporal characteristics, a spatiotemporal variability function is constructed using the Kriging interpolation method to describe the variation of temperature in different regions and at different times, thereby providing a data foundation for the subsequent establishment of a temperature field distribution model.

[0022] Combining the aforementioned spatiotemporal characteristics, a three-dimensional temperature field distribution model is established using the finite element method (FEM). The FEM discretizes the kiln space into a finite number of elements, and simulates the overall temperature distribution by solving the heat conduction equation for each element, describing how heat is transferred from high-temperature zones to low-temperature zones. Real-time temperature data is input into the model as boundary conditions, and an iterative solution generates a temperature field mapping. The iterative solution uses the Newton-Raphson method to approximate the desired solution. The Newton-Raphson method is a nonlinear equation solving technique that converges to an accurate value through linear approximation and repeated corrections, ultimately obtaining the initial temperature field mapping reflecting each region. This initial temperature field mapping can also be visualized as a mesh plot, displaying the temperature gradient of each region. For example, in a kiln for producing split toilets, the model generated after its construction... The mapping shows that the temperature in the center of the firing zone is higher than that at the edge, reflecting the uneven heat distribution. This provides a basis for adjusting the heating elements, and the beneficial effects are optimized energy consumption and improved product quality consistency. For continuous kilns, dynamic simulation can also be incorporated to generate a 24-hour cycle temperature field mapping, revealing the impact of nighttime cooling and helping to maintain a stable firing environment. In intermittent kiln applications, model building emphasizes batch-to-batch variation, and the generated initial temperature field mapping highlights the spatiotemporal characteristics of the preheating stage, supporting rapid iterative adjustments. The initial temperature field mapping reflects the temperature differences in various regions within the kiln, providing a data foundation for subsequent control unit analysis. For example, the initial temperature field mapping displays differences using color coding, such as red for high-temperature zones and blue for low-temperature zones, which is directly input into the difference analysis module of the control unit.

[0023] Based on this, the acquired environmental variable data is preprocessed to filter out noise interference and retain key factors related to the temperature field, such as oxygen content and humidity. During the preprocessing process, a median filter is used to remove sudden noise, ensuring that environmental variable information that can affect the temperature field is retained. The preprocessed environmental variable data is stored together with the initial temperature field mapping for subsequent dynamic adjustment. A key-value pair method is used, with the timestamp as the key and the temperature field mapping grid point as the value, to facilitate subsequent retrieval and adjustment. The final generated initial temperature field mapping not only reflects the temperature differences in various areas within the kiln but also provides a data foundation for the analysis and adjustment of the subsequent control unit. The above technical solution, by accurately acquiring temperature and environmental variable data and combining advanced data processing methods and algorithm models, ensures accurate modeling and optimized control of the temperature field within the kiln, thereby improving the quality consistency and production efficiency of split toilet production.

[0024] Step S2: Calculate the output difference index between the output temperature value and the expected temperature target value corresponding to each control unit based on the initial temperature field mapping. Analyze the coordination between control units based on the difference index and the neural network model, identify areas of coordination deficiency, and obtain coordination deficiency indices; specifically including: Temperature distribution data corresponding to each control unit is extracted from the initial temperature field mapping; the deviation between the output temperature value of each control unit and the expected temperature target value is compared to calculate the output difference index; the output difference index is processed using a pre-trained neural network model to analyze the coordination between control units; the coordination missing probability value of each region is output through the neural network model; the location and range of the coordination missing region are determined based on the coordination missing probability value; key features are extracted from the coordination missing region to generate the coordination missing index; the coordination missing index is compared with historical data to verify its accuracy.

[0025] Specifically, temperature data for each control unit in its corresponding region is extracted from the initial temperature field mapping, and this data is organized into a distribution matrix. Next, the current output temperature value of each control unit is compared with the preset target temperature value, and the deviation between the corresponding output temperature value of each control unit and the muboa temperature value is calculated. The root mean square value of all deviations is summarized as the output difference index, which provides a quantitative basis for subsequent analysis. A pre-trained neural network model is used to process the output difference index and analyze the coordination between control units. This neural network model is trained using training data based on a neural network algorithm, including historical output difference index data between control units and corresponding coordination missing probability values. Specifically, the output difference index is fed as an input vector into the neural network model, which includes an input layer, a hidden layer, and an output layer. The ReLU activation function of the hidden layer is used to process the nonlinear relationship, and the coordination correlation coefficient between control units is calculated. This coordination correlation coefficient reflects the degree of consistency in the output of the control units. The neural network model transforms the differences into a coordination index through forward propagation. If the coordination correlation coefficient is lower than the preset value, it indicates insufficient coordination; conversely, it indicates good coordination between control units.

[0026] By applying the softmax function to the output layer of the aforementioned neural network model, the hidden layer results are converted into a probability distribution, and the probability value of coordination deficiency in each region is output. This probability value reflects the risk of insufficient coordination in temperature regulation in each region. For example, a low probability value indicates a smaller risk of coordination deficiency in a region, while a high probability value indicates a larger risk. Based on the above probability values, the location and range of the coordination deficiency region are further determined. Specifically, when the probability value exceeds a set threshold, a clustering algorithm such as K-means is used to group the high probability points, determine the specific location of the deficiency region, and calculate the center position and radius of the region to accurately delineate the range of the deficiency region. Key features, such as temperature gradient, temperature peak, and fluctuation variance, are extracted from the determined coordination deficiency region, and a coordination deficiency index is generated by weighted summation. This coordination deficiency index comprehensively considers the importance of different features in temperature regulation and can reflect the uniformity and stability of the temperature distribution in the region. To ensure that the coordination deficiency index can adapt to the needs of different scenarios, these feature values ​​are normalized to a range of 0 to 1, which facilitates comparison and verification with historical data.

[0027] The generated coordination missing index is compared with historical data to verify its accuracy. Specifically, by querying similar area index records in the historical database, the difference between the current coordination missing index and the historical average is calculated. If the difference is less than a preset threshold, it indicates that the index has high accuracy and can be used as a basis for subsequent adjustments. Through the above technical solution, uneven areas of temperature control in the kiln can be effectively identified, and through precise coordination missing analysis, data support can be provided for subsequent control unit adjustments, thereby achieving uniformity of the temperature field and improving production efficiency, ultimately ensuring the efficient operation of the kiln's temperature control system during the production of split toilets.

[0028] Step S3: If the coordination missing index exceeds a preset threshold, real-time environmental variables are obtained from the dynamic environment, and the environmental variable data is fused to determine the sequence of control units that need to be adjusted; specifically including: The system monitors the changing trend of the coordination missing index in real time; if the coordination missing index exceeds a preset threshold, an environmental variable acquisition mechanism is triggered; real-time humidity, airflow, and pressure data are acquired from the dynamic environment of the kiln through the sensor network; the real-time environmental variable data are standardized to eliminate dimensional differences; the standardized environmental variable data are fused with the initial temperature field to analyze the influence of the environment on the temperature field; based on the analysis results, control units related to the coordination missing area are determined, and the sequence of control units that need to be adjusted is generated.

[0029] Specifically, by continuously tracking and coordinating changes in missing indicator values ​​in real time—for example, collecting data at regular intervals to form time-series data—and calculating the rate of increase or decrease of the indicators, potential temperature regulation problems can be identified. When the missing indicator exceeds a preset threshold, an environmental variable collection mechanism is triggered. A sensor network deployed in various areas of the kiln collects environmental data such as humidity, airflow, and pressure in real time. To eliminate dimensional differences, all real-time collected environmental variable data undergoes standardization, typically using a min-max standardization method to map humidity, airflow, and pressure data to a unified range, ensuring data comparability. The standardized environmental data is then fused with the initial temperature field mapping to analyze the impact of environmental factors on the temperature field distribution. A linear regression model is used to analyze the relationship between temperature field changes and environmental variables, calculating the influence coefficient of each environmental variable on the temperature field, thereby identifying which areas are affected by environmental factors such as humidity, airflow, and pressure. The influence of airflow is significant, thus identifying control units related to the missing coordination areas. For example, in the central area of ​​the kiln, if the airflow data influence coefficient is 0.7 and the humidity influence coefficient is 0.6, the fused analysis shows that the temperature in this area is significantly affected by airflow, resulting in a fluctuation deviation of up to 10%, thus optimizing subsequent adjustments. Finally, based on the above analysis results, a sequence of control units required for adjustment is generated, providing target objects for subsequent parameter calculations. This allows for optimization of the temperature field distribution and ensures temperature uniformity by adjusting the output settings of the control units. Through the above technical solution, the non-uniformity of the temperature field can be responded to in real time during toilet production. Combined with dynamic environmental variables, temperature control can be precisely adjusted, improving production efficiency, reducing energy waste, and ensuring the quality consistency of split toilet products. Furthermore, when dealing with temperature control in different areas, the area requiring adjustment can be accurately located based on actual environmental conditions and the coordination between control units, thus providing an intelligent and flexible temperature control solution.

[0030] Step S4: Calculate the connection parameters for the control unit sequence to obtain a smooth transition parameter set; update the output settings of multiple control units through the smooth transition parameter set to determine whether the temperature fluctuation deviation has decreased; if the deviation reduction is confirmed, obtain the overall temperature data of the kiln and analyze the data distribution uniformity to determine the degree of achievement of the uniform distribution target; In step S4, the connection parameters are calculated for the control unit sequence to obtain a set of smooth transition parameters, including: Extract the current output parameters of each unit from the sequence of control units that need adjustment; analyze the output connection relationship between each control unit using a fuzzy logic algorithm; calculate the connection parameter values ​​between each control unit according to the fuzzy logic algorithm; extract smooth transition features from the connection parameter values ​​to generate the smooth transition parameter set; verify the applicability of the smooth transition parameter set under different operating conditions; balance the output differences between each control unit and optimize the temperature field distribution by using the smooth transition parameter set.

[0031] Specifically, the current output parameters of each control unit are extracted from the sequence of control units that need adjustment. These current output parameters include, but are not limited to, the output power and temperature setpoint of each unit, reflecting the real-time operating status of each unit and providing a data foundation for subsequent analysis. Using these output parameters, a fuzzy logic algorithm is employed to analyze the output connection relationship between the control units. The fuzzy logic algorithm, based on fuzzy set theory, is used to handle the uncertainty and nonlinear relationships present in temperature fluctuations. The output parameters of the control units are first converted into fuzzy input variables and then fuzzified by defining appropriate membership functions such as low, medium, and high. A fuzzy rule base is established, for example, setting rules such as "if unit A has high output power and unit B has low output power, then the connection relationship is unstable." The fuzzy inference engine calculates the fuzzy value of the connection relationship and uses a defuzzification method to convert the fuzzy value into quantified connection parameter values. These connection parameter values ​​reflect the degree of coordination between the control units. For example, ... Figures 2-3 As shown, in the scenario of producing split toilets in a kiln, assuming that the output power ratio of unit A is 80% and the output power ratio of unit B is 50%, the fuzzy logic algorithm analyzes that the connection relationship value is 0.6, which indicates moderate instability and is beneficial for early identification of potential temperature deviations. The above-mentioned output power ratio is the ratio between the actual output power and the maximum output power.

[0032] Based on the calculated transition parameter values, smooth transition features are further extracted to generate a smooth transition parameter set. This includes statistical analysis of the transition parameter value sequence, such as calculating its mean and variance, to extract smooth transition features, such as transition smoothness. These smooth transition features reflect the smoothness of parameter value changes. By setting a smoothness threshold and according to different kiln conditions, such as heating and cooling stages, an adaptive parameter set is generated. This parameter set is adjusted within different temperature ranges to ensure a stable temperature transition between control units. Specifically, in the more complex high-temperature firing stage, a more adaptive transition parameter set is generated, further optimizing the uniformity of the temperature field by gradually reducing the differences between control units. To verify the applicability of the generated smooth transition parameter set under different operating conditions, different kiln conditions, such as temperature change rate conditions, are simulated to test its control effect on temperature fluctuations. If the temperature fluctuation is within the preset threshold... This demonstrates that the parameter set can effectively control temperature fluctuations and ensure a uniform temperature field distribution under specific operating conditions. Using this smooth transition parameter set, the output of each control unit is adjusted through a control algorithm to balance their output differences and optimize the temperature field distribution. For example, if the temperature deviation in a certain area is large, the output power of the relevant control units is adjusted according to the smooth transition parameter set to ensure that the temperature in that area gradually approaches the target temperature. This effectively reduces temperature differences in the kiln, thereby reducing temperature fluctuations and unevenness, and ultimately improving the temperature control accuracy in the production of split toilets. Through the above technical solution, the generated smooth transition parameter set will be stored as a reference for subsequent control unit adjustments, providing stable parameter support for future control processes, ensuring the continuity and consistency of temperature fluctuation control. Through feedback mechanisms and parameter adjustments, the accuracy and stability of temperature control during the production of split toilets can be achieved, further improving production efficiency and product quality.

[0033] Further, in step S4, updating the output settings of multiple control units using the smooth transition parameter set includes: The output power and response time of each control unit are adjusted according to the smooth transition parameter set; the output status of each control unit is monitored in real time after the update, and temperature fluctuation data is recorded; the fluctuation amplitude and frequency characteristics are extracted from the temperature fluctuation data; the change trends of the fluctuation amplitude and frequency characteristics before and after the update are compared; the temperature fluctuation deviation is determined according to the change trend; if the temperature fluctuation deviation is reduced, a deviation reduction confirmation signal is generated; and the deviation reduction confirmation signal is fed back to the control system.

[0034] Specifically, the output power and response time of each control unit are adjusted according to the smooth transition parameter set to achieve a smooth transition in temperature regulation. Key values ​​such as power adjustment ratio and response time are extracted from the pre-calculated smooth transition parameter set and applied to adjust each control unit, changing the output power and response speed of its heating element. The output status of the control units after adjustment is monitored in real time, i.e., the output power of each unit and the temperature of the corresponding area are continuously collected using a sensor network. Simultaneously, temperature fluctuation data of the control units is continuously recorded, generating a temperature fluctuation record. Based on this, fluctuation amplitude and frequency characteristics are extracted from the temperature fluctuation data to compare the changing trends of fluctuation amplitude and frequency characteristics before and after the update. Specifically, a Fourier transform is performed on the temperature fluctuation record to calculate the amplitude spectrum and frequency spectrum of the temperature fluctuation. The peak amplitude is extracted from the amplitude spectrum as the fluctuation amplitude characteristic, and the dominant frequency is extracted from the frequency spectrum as the frequency characteristic. Based on these characteristics, it is determined whether the temperature fluctuation has been effectively controlled. If the trend shows that the amplitude of the temperature fluctuation decreases and the frequency decreases, it indicates that the temperature control has stabilized, and a deviation reduction confirmation signal is generated.

[0035] The deviation reduction confirmation signal is a digital signal generated by a predefined logic gate circuit. This signal includes a timestamp and a deviation quantization value, and is encoded using a standard protocol format (such as Modbus) for transmission in the kiln control network. After signal generation, the system immediately verifies its integrity to ensure error-free signal transmission. The generated deviation reduction confirmation signal is fed back to the control system as a basis for subsequent overall temperature analysis. Upon receiving the signal, the central processing unit updates the status register for the fusion analysis of overall temperature data, thereby providing accurate data support for future temperature regulation. This technical solution, through the aforementioned closed-loop control process, continuously optimizes the temperature coordination between control units, ensuring the uniformity of the kiln temperature field during the production of split toilets, ultimately improving product quality and production efficiency.

[0036] Further, in step S4, the uniformity of data distribution is analyzed to determine the degree of achievement of the uniform distribution target, including: Upon receiving the deviation reduction confirmation signal, the overall temperature data acquisition process is triggered; real-time temperature data of each area within the kiln is acquired through the sensor network; spatial distribution analysis is performed on the real-time temperature data to extract uniformity features; an information processing algorithm is used to calculate the matching degree between the uniformity features and the target uniform distribution; the degree of achievement of the uniform distribution target is determined based on the matching degree; the degree of achievement of the uniform distribution target is compared with historical records to analyze the sustainability of temperature field optimization.

[0037] Specifically, if the deviation reduction is confirmed, the overall temperature data of the kiln is acquired. First, a deviation reduction confirmation signal is received, triggering the overall temperature data acquisition process. The receipt of the above confirmation signal will activate the preset acquisition module, ensuring that the temperature data acquisition process is started synchronously from all areas of the kiln. Through the sensor network, the temperature data of each area in the kiln is acquired in real time, ensuring coverage of key areas such as the kiln's entrance area, middle area, and exit area. The temperature data of each area will be transmitted to the central processing unit through the sensor network to form a data stream. The acquired real-time temperature data is spatially distributed and uniformity features are extracted. Specifically, the temperature data is mapped to the kiln's three-dimensional coordinate system to generate a temperature distribution grid. By calculating the temperature gradient between adjacent grid points, the uniformity of the temperature distribution is further evaluated. At this time, the matching degree between the uniformity features and the target uniform distribution is calculated. Methods such as cosine similarity or Euclidean distance are used to quantify the closeness of the current temperature field to the ideal uniform distribution, thereby obtaining the matching degree.

[0038] Based on the calculated matching degree, the degree of achievement of the uniform distribution target, i.e., the matching degree, is further determined. If the matching degree is high, i.e., greater than the set matching degree, it indicates that the temperature field is close to the ideal state. If the matching degree is low, i.e., less than or equal to the set matching degree, it indicates that there is still room for optimization. The current degree of achievement of the uniform distribution target is compared with the historical records to analyze the sustainability of temperature field optimization. Specifically, the achievement records over a period of time are retrieved from the database, and the difference between the current achievement control system and the historical average is calculated. If the difference persists for multiple periods and is in the same direction, it indicates that the optimization of the temperature field is sustainable, and the stability of the optimization process can be predicted, providing a basis for subsequent temperature adjustments. By comparing with historical records, the adaptability of temperature field optimization can also be evaluated, especially under different seasons or changes in the external environment. In this way, the system can automatically adjust the acquisition frequency according to changes in environmental variables to adapt to different stages of kiln operation and production needs. If the degree of achievement of the uniform distribution target is high, it indicates that the current optimization effect is good, and the acquisition frequency is reduced to maintain the stability of the control system. If the degree of achievement is low, the data acquisition frequency is increased to enable more timely temperature control.

[0039] Step S5: Adjust the acquisition frequency of the sensor network according to the degree of achievement of the uniform distribution target to obtain the optimized temperature field mapping; specifically including: The temperature field stability index is extracted from the uniform distribution target achievement degree; the direction of the acquisition frequency adjustment is determined based on the comparison result of the stability index and the preset threshold; if the stability index is lower than the preset threshold, the acquisition frequency of the sensor network is increased; if the stability index is higher than the preset threshold, the acquisition frequency of the sensor network is decreased; temperature data and environmental variable data are reacquired according to the adjusted acquisition frequency; the temperature field distribution characteristics are updated from the reacquired data to generate the optimized temperature field mapping; the coordinated control mechanism of the kiln temperature field is maintained through the optimized temperature field mapping.

[0040] Specifically, based on the achievement of the aforementioned uniform distribution target, a temperature field stability index is first extracted. This stability index is obtained by calculating the standard deviation of the temperature field. A smaller standard deviation indicates a more uniform temperature distribution, thus indicating higher temperature field stability. By comparing the extracted stability index with a preset threshold, it is determined whether the sensor network's acquisition frequency needs adjustment. If the stability index is lower than the preset threshold, it means the temperature distribution is uneven, and the sensor network's acquisition frequency is increased to collect data more frequently and further optimize temperature control. If the stability index is higher than or equal to the preset threshold, it indicates a relatively uniform temperature distribution, and the acquisition frequency is reduced. To save sensor resources, after adjusting the acquisition frequency, temperature and environmental variable data of each area of ​​the toilet production kiln are reacquired according to the new acquisition frequency. By analyzing the reacquired data, the temperature field distribution characteristics are updated, and an optimized temperature field mapping is generated. The above temperature field reflects the adjusted temperature field distribution, ensuring that the temperature of the kiln is more uniform. The optimized temperature field mapping not only provides accurate data for temperature control, but also maintains the coordinated control mechanism of the kiln temperature field. Specifically, the above mapping is fed back to the control unit to adjust the output settings of each control unit to maintain the temperature coordination of each area in the kiln and reduce local overheating or overcooling.

[0041] The above technical solution can dynamically adjust the temperature control strategy based on real-time data and environmental changes, ensuring the uniformity of the kiln temperature field, improving the quality and efficiency of split toilet production, and by continuously optimizing the temperature field mapping and adjusting the output of the control unit, the kiln can maintain good temperature coordination at different production stages, avoiding uneven temperature or thermal fluctuations during production, thereby improving the stability of the production process and the quality of the final product.

[0042] like Figure 4 The diagram shown illustrates the system architecture for temperature control throughout the production process of the split-type toilet in this embodiment.

[0043] This invention also provides a temperature control system for the production of split toilets, used to implement the above-mentioned method, such as... Figure 5 As shown, the system includes: The temperature mapping unit is used to collect temperature data and environmental variable data of various areas of the kiln in real time during the production of split toilets through a sensor network, and extract temperature field distribution characteristics from the temperature data to obtain an initial temperature field mapping. The difference analysis unit is used to calculate the output difference index between the output temperature value and the expected temperature target value of each control unit according to the initial temperature field mapping, analyze the coordination between control units based on the difference index and the neural network model, determine the coordination missing area and obtain the coordination missing index. The data fusion unit is used to obtain real-time environmental variables from the dynamic environment and fuse the environmental variable data to determine the sequence of control units that need to be adjusted if the coordination missing index exceeds a preset threshold. The output adjustment unit is used to calculate the connection parameters for the control unit sequence to obtain a smooth transition parameter set; update the output settings of multiple control units through the smooth transition parameter set to determine whether the temperature fluctuation deviation has decreased; if the deviation reduction is confirmed, acquire the overall temperature data of the kiln and analyze the data distribution uniformity to determine the degree of achievement of the uniform distribution target; A frequency adjustment unit is used to adjust the acquisition frequency of the sensor network according to the degree of achievement of the uniform distribution target, so as to obtain an optimized temperature field mapping.

[0044] The present invention also provides a computer-readable storage medium storing instructions that, when executed by a processor, implement the above-described method.

[0045] In summary, this invention uses a sensor network to collect real-time temperature and environmental variable data from various areas of the kiln and generates an initial temperature field mapping, providing a foundation for subsequent temperature control adjustments. This helps to clarify temperature differences between different areas and identify potential temperature unevenness issues. Next, by analyzing the initial temperature field mapping data, the difference index between the output temperature of each control unit (such as the heating element) and the expected temperature target value is calculated. Combined with a neural network model, the coordination between control units is further analyzed to identify areas of coordination deficiency requiring adjustment, providing a basis for adjustment schemes. When a coordination deficiency area is identified, real-time environmental variables such as humidity and airflow are obtained from the dynamic environment, and the above data is integrated to optimize and adjust the temperature control strategy. This dynamically determines which control units need adjustment, forming a new control unit sequence. Furthermore, connection parameters are calculated, and the output settings of multiple control units are optimized and adjusted using a smooth transition parameter set, thereby reducing temperature fluctuation deviations. By determining whether temperature fluctuations have decreased, the stability and uniformity of the temperature field are ensured. After optimizing the output settings of the control unit, the degree of achievement of temperature field optimization is further determined by analyzing the distribution uniformity of the overall temperature data. The acquisition frequency of the sensor network is adjusted according to the degree of uniform distribution target achievement. Through adaptive adjustment of the acquisition frequency, the temperature distribution can be monitored more accurately in real time, and an optimized temperature field mapping can be generated according to needs. Through the cooperation of the above technical solutions, the temperature control system can continuously provide uniform and accurate temperature regulation during the production of two-piece toilets. This not only optimizes the temperature control accuracy, reduces energy consumption, and improves production efficiency, but also copes with the challenges of different production stages and environmental conditions, ensuring that each link operates in the optimal state, and ultimately achieving the production of high-quality two-piece toilets.

[0046] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0047] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0048] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A temperature control method for manufacturing split-type toilets, characterized in that, include: Step S1: Collect temperature data and environmental variable data of each area of ​​the kiln in real time during the production of the split toilet through a sensor network, and extract temperature field distribution characteristics from the temperature data to obtain the initial temperature field mapping. Step S2: Calculate the output difference index between the output temperature value and the expected temperature target value of each control unit according to the initial temperature field mapping. Analyze the coordination between control units based on the difference index and the neural network model, determine the coordination gap area, and obtain the coordination gap index. Step S3: If the coordination missing index exceeds a preset threshold, real-time environmental variables are obtained from the dynamic environment, and the environmental variable data is fused to determine the control unit sequence that needs to be adjusted; Step S4: Calculate the connection parameters for the control unit sequence to obtain a smooth transition parameter set; update the output settings of multiple control units using the smooth transition parameter set to determine whether the temperature fluctuation deviation has decreased; if the deviation reduction is confirmed, acquire the overall kiln temperature data and analyze the data distribution uniformity to determine the degree of achievement of the uniform distribution target; wherein, calculating the connection parameters for the control unit sequence to obtain the smooth transition parameter set includes: extracting the current output parameters of each unit from the control unit sequence that needs adjustment; analyzing the output connection relationship between each control unit using a fuzzy logic algorithm; calculating the connection parameter values ​​between each control unit according to the fuzzy logic algorithm; extracting smooth transition features from the connection parameter values ​​to generate the smooth transition parameter set; verifying the applicability of the smooth transition parameter set under different operating conditions; balancing the output differences between each control unit and optimizing the temperature field distribution using the smooth transition parameter set; Step S5: Adjust the acquisition frequency of the sensor network according to the uniform distribution target achievement degree to obtain an optimized temperature field mapping, including: extracting a temperature field stability index from the uniform distribution target achievement degree; determining the acquisition frequency adjustment direction based on the comparison result of the stability index and a preset threshold; increasing the acquisition frequency of the sensor network if the stability index is lower than the preset threshold; decreasing the acquisition frequency of the sensor network if the stability index is higher than the preset threshold; re-acquiring temperature data and environmental variable data according to the adjusted acquisition frequency; updating the temperature field distribution characteristics from the re-acquired data to generate an optimized temperature field mapping; and maintaining the collaborative control mechanism of the kiln temperature field through the optimized temperature field mapping.

2. The method as described in claim 1, characterized in that, Step S1 includes: During the production of the split toilet, a sensor network deployed in various areas of the kiln monitors temperature changes and environmental variables in real time. Multiple temperature data points and corresponding environmental conditions are acquired from the sensor network. Feature extraction is performed on the temperature data to analyze the spatiotemporal characteristics of temperature distribution in each area. A temperature field distribution model is constructed based on these spatiotemporal characteristics to generate the initial temperature field mapping. The environmental variable data is preprocessed to filter out noise interference and retain influencing factors related to the temperature field. The preprocessed environmental variable data is then associated and stored with the initial temperature field mapping.

3. The method as described in claim 1, characterized in that, Step S2 includes: Temperature distribution data corresponding to each control unit is extracted from the initial temperature field mapping; the deviation between the output temperature value of each control unit and the expected temperature target value is compared to calculate the output difference index; the output difference index is processed using a pre-trained neural network model to analyze the coordination between control units; the coordination missing probability value of each region is output through the neural network model; the location and range of the coordination missing region are determined based on the coordination missing probability value; key features are extracted from the coordination missing region to generate the coordination missing index; the coordination missing index is compared with historical data to verify its accuracy.

4. The method as described in claim 1, characterized in that, Step S3, integrating the environmental variable data to determine the sequence of control units that need to be adjusted, including: The system monitors the changing trend of the coordination missing index in real time; if the coordination missing index exceeds a preset threshold, an environmental variable acquisition mechanism is triggered; real-time humidity, airflow, and pressure data are acquired from the dynamic environment of the kiln through the sensor network; the real-time environmental variable data are standardized to eliminate dimensional differences; the standardized environmental variable data are fused with the initial temperature field to analyze the influence of the environment on the temperature field; based on the analysis results, control units related to the coordination missing area are determined, and the sequence of control units that need to be adjusted is generated.

5. The method as described in claim 1, characterized in that, In step S4, the output settings of multiple control units are updated using the smooth transition parameter set, including: The output power and response time of each control unit are adjusted according to the smooth transition parameter set; the output status of each control unit is monitored in real time after the update, and temperature fluctuation data is recorded; the fluctuation amplitude and frequency characteristics are extracted from the temperature fluctuation data; the change trends of the fluctuation amplitude and frequency characteristics before and after the update are compared; the temperature fluctuation deviation is determined according to the change trend; if the temperature fluctuation deviation is reduced, a deviation reduction confirmation signal is generated; and the deviation reduction confirmation signal is fed back to the control system.

6. The method as described in claim 1, characterized in that, In step S4, the uniformity of data distribution is analyzed to determine the degree of achievement of the uniform distribution target, including: Upon receiving a confirmation signal indicating a reduction in deviation, the overall temperature data acquisition process is triggered. Real-time temperature data for each region within the kiln is acquired through the sensor network. Spatial distribution analysis is performed on the real-time temperature data to extract uniformity features. An information processing algorithm is used to calculate the matching degree between the uniformity features and the target uniform distribution. The degree of achievement of the uniform distribution target is determined based on the matching degree. The degree of achievement of the uniform distribution target is compared with historical records to analyze the sustainability of temperature field optimization.

7. A temperature control system for manufacturing split toilets, used to implement the method as described in any one of claims 1-6, characterized in that, The system includes: The temperature mapping unit is used to collect temperature data and environmental variable data of various areas of the kiln in real time during the production of split toilets through a sensor network, and extract temperature field distribution characteristics from the temperature data to obtain an initial temperature field mapping. The difference analysis unit is used to calculate the output difference index between the output temperature value and the expected temperature target value of each control unit according to the initial temperature field mapping, analyze the coordination between control units based on the difference index and the neural network model, determine the coordination missing area and obtain the coordination missing index. The data fusion unit is used to obtain real-time environmental variables from the dynamic environment and fuse the environmental variable data to determine the sequence of control units that need to be adjusted if the coordination missing index exceeds a preset threshold. The output adjustment unit is used to calculate the connection parameters for the control unit sequence to obtain a smooth transition parameter set; update the output settings of multiple control units through the smooth transition parameter set to determine whether the temperature fluctuation deviation has decreased; if the deviation reduction is confirmed, acquire the overall temperature data of the kiln and analyze the data distribution uniformity to determine the degree of achievement of the uniform distribution target; A frequency adjustment unit is used to adjust the acquisition frequency of the sensor network according to the degree of achievement of the uniform distribution target, so as to obtain an optimized temperature field mapping.

8. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the method as described in any one of claims 1-6.

Images